Agents-internal

About this Agent

The Invoice Validation Agent is an AI digital worker designed to revolutionize the Accounts Payable department by automating the invoice verification process. This intelligent agent matches incoming invoices with corresponding purchase orders and delivery records to identify any discrepancies in real-time. By streamlining the accounts payable process, it ensures transactional accuracy and enhances operational efficiency, allowing finance teams to focus on strategic tasks rather than manual verification.

Accuracy
TBD

Speed
TBD

Input Data Set

Sample of data set required for Invoice Validation Agent:

Delivery Number	PO Number	Date	Line Item	Quantity
DEL001	PO1001	2024-09-28	Widgets	10
DEL002	PO1002	2024-09-30	Gadgets	5

Invoice Number	Supplier Name	Date	Total Amount	PO Number	Line Item	Quantity	Unit Price
INV001	Johnston Supplies	2024-10-01	1500.0	PO1001	Widgets	10	150
INV002	Murray Imports	2024-10-02	2500.0	PO1002	Gadgets	5	500

PO Number	Supplier Name	Date	Total Amount	Line Item	Quantity	Unit Price
PO1001	Johnston Supplies	2024-09-25	1500.0	Widgets	10	150
PO1002	Murray Imports	2024-09-27	2500.0	Gadgets	5	500

Deliverable Example

Sample output delivered by the Invoice Validation Agent:

Invoice Number	Status	Discrepancy Details
INV001	Valid	No discrepancies found
INV002	Invalid	Price mismatch: PO amount is 2000, but invoice amount is 2500

ZBrain credits and their usage

A credit is a unit of usage on ZBrain. Credits are consumed whenever you perform actions such as embedding documents or querying an app. Here’s how credits are utilized:

Document Embedding:

When you upload a document, it is processed and embedded to create a searchable vector representation. This step consumes credits based on the size of the document and the embedding model used.

Input Processing:

When you ask a question, the relevant context is retrieved from the embeddings and processed by the Large Language Model (LLM). This step incurs a credit cost based on the model and the number of input tokens.

Generating Output

The LLM then generates a response based on the processed input, consuming additional credits based on the number of output tokens.

The cost in credits for various models and processes is detailed below:

Models and Credit Consumption:

Model	Input Cost	Output Cost
GPT-4o	2,500 credits / 1M tokens	7,500 credits / 1M tokens
GPT-4	15,000 credits / 1M tokens	30,000 credits / 1M tokens
GPT-4-32k	30,000 credits / 1M tokens	60,000 credits / 1M tokens
GPT-3.5 Turbo	250 credits / 1M tokens	750 credits / 1M tokens

Embedding Models:

Model	Input Cost
text-embedding-3-small	20 credits / 1M tokens
text-embedding-3-large	130 credits / 1M tokens
ada v2	100 credits / 1M tokens

When you create a knowledge base or query an app, credits are deducted based on the embedding, input, and output token usage. This ensures you only pay for what you use while leveraging the full power of advanced AI models.

Invoice Validation Agent

About this Agent

Input Data Set

Deliverable Example

Company

Product

Contact us

Get more information

In this personalized demo, you will:

Explore ZBrain Platform

Discover Workflow Integrations

Engage in Q&A Session